检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： Guoying Zhao Li Cui Hua Li M. Pietikainen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering University of Oulu Finland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Mathematics Science Beijing Normal University Beijing China

Video-based gait recognition is a challenging problem in computer vision. In this paper, fractal scale wavelet analysis is applied to describe and automatically recognize gait. Fractal scale based on wavelet analysis represents the self-similarity of signals, and improves the flexibility of wavelet moments. Optimal wavelets based on generalized multi-resolution analysis are used to improve the recognition rate. Descriptors of fractal scale are translation, scale and rotation invariant. Moreover, a combination of fractal scale and wavelet moments improves the recognition rate. Experiments show that the proposed descriptor is efficient for gait recognition

关键词： Fractals Wavelet analysis Image recognition Signal resolution Image sequences Continuous wavelet transforms Discrete wavelet transforms Wavelet coefficients Machine vision Laboratories

来源：评论

学校读者我要写书评

暂无评论

Dim Small Targets Detection Based on Dualband Infrared Image Fusion

Dim Small Targets Detection Based on Dualband Infrared Image...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Yu-Qiu Sun Jin-Wen Tian Jian Liu State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recongnition and Artificial Intelliegence Huazhong University of Science and Technology Wuhan China School of Information and Mathematics Yangtze University Jingzhou China State Education Commission Key Laboratory for Image Processing and Intelligent Control Department of Electronic Information and Enginery Huazhong University of Science and Technology Wuhan China

To infrared images, the contrast of target and background is low, dim small targets have no concrete shapes and their textures cannot be reliable predicted. The paper puts forward a novel algorithm to fuse mid-wave and long-wave infrared images and detect targets. Firstly, the source images are decomposed by wavelet transformation. In usual, targets in infrared images are man-made, and their fractal dimension is different comparing with natural background. In wavelet transformation domain high-frequency part, we calculate local fractal dimension and set up fusion rule to merge corresponding sub-images of two matching source images. In low-frequency, we extract local maximum gray level to fuse them. Then reconstruct image by wavelet inverse transformation and obtain fused result image. In fusion results, the contrast between targets and background has obvious changes. And targets can be detected using contrast thresholding. The experimental results show that the method using fractal dimension to fuse dualband infrared images, and then detect targets is superior to use mid-wave or long -wave infrared images detect targets alone.

关键词： Object detection Dual band Infrared imaging Infrared detectors Image fusion Fuses Fractals Concrete Shape Wavelet domain

来源：评论

学校读者我要写书评

暂无评论

Dualband Infrared Images Target Detection Algorithm Based on Multiscale Morphology

Dualband Infrared Images Target Detection Algorithm Based on...

引用

2006 8th International Conference on Signal processing

作者： Yuqiu Sun Jinwen Tian Jian Liu School of Information and Mathematics Yangtze University State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial IntelligenceHuazhong University of Science and Technology

According to the features of mid-wave and long-wave infrared images,they are decomposed into morphology pyramid respectively based on the new multiscale mathematical morphology filters proposed in the *** features such as local maximum gray level and average gradient strength of every image are extracted at each level of morphology *** dualband infrared images based on fusion rule put forward in the paper,and then reconstruct original image and detect target using contrast threshold *** experiment results show that dualband infrared images target detection algorithm based on multiscale morphology algorithm is better than use mid-wave or long-wave infrared images detect targets alone.

关键词： image Dualband Infrared Images Target Detection Algorithm Based on Multiscale Morphology Target

来源：评论

学校读者我要写书评

暂无评论

CNNUM-Based Methods Using Deformable Contours on Smooth Boundaries

CNNUM-Based Methods Using Deformable Contours on Smooth Boun...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Tamas Szabo Peter Szolgay Department of Image Processing and Neurocomputing Faculty of Information Technology University of Pannonia Veszprem Hungary Analogical and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this paper two methods are presented. A CNNUM-based method is shown to quantify the displacement of the normal interhemisperic bilateral symmetry line. The method uses a deformable open contouring technique. Anothe... 详细信息

关键词： Active contours Computed tomography Magnetic resonance Anatomical structure Image segmentation Biomedical imaging Electronic mail Computer networks Pixel Image resolution

来源：评论

学校读者我要写书评

暂无评论

Method of color transfer between images

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2006年第10期18卷 1513-1518页

作者： Wang, Shaorong Li, Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University of Chinese Academy of Sciences Beijing 100049 China

The current color transfer methods always use statistics as transfer function and can not deal with images with lower similarity. In this paper, a section by section color transfer method is presented, in which all the source images and reference images are segmented into a series of homogeneous regions, in which variations between classes are big and variations within classes are small, and then the color between the corresponding regions are transferred. The experiments show that the algorithm is efficient, the results are satisfactory, and it can be applied to complicated images with lower similarity.

关键词： Color transfer Linear transform OTSU's method

来源：评论

学校读者我要写书评

暂无评论

Fusing color and gradient features approach to real-time background subtraction using graph cuts

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2006年第11期18卷 1741-1747页

作者： Deng, Yu Li, Zhenbo Li, Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Acad. of Sciences Beijing 100080 China National Research Center for Intelligent Computing Systems Beijing 100080 China Graduate University Chinese Acad. of Sciences Beijing 100049 China

Based on the fusion of color and gradient features, this paper implements a novel approach to real-time background subtraction. Firstly, an energy function is defined based on the fusion of color and gradient features. Secondly, the graph cuts based algorithm is employed to minimize energy function and segment the foreground. Finally, average optical flow is used to make inference about the validity of foreground regions, background models are then updated. The experimental results of different real scenes show that the proposed approach can produce real-time detection and promising results.

关键词： Background subtraction Color and gradient feature Energy function Graph cuts Real-time detection

来源：评论

学校读者我要写书评

暂无评论

Novel linear edge detector derived from Fresnel diffraction mode

引用

Jisuanji Xuebao/Chinese Journal of Computers 2006年第12期29卷 2138-2142页

作者： Diao, Lu-Hong Yu, Bin Li, Hua National Center of Computing Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University Chinese Academy of Sciences Beijing 100049 China Institute of Optoelectronics Shenzhen University Shenzhen 518600 China

This paper proposes an edge detection scheme based on Fresnel diffraction mode. Since Fresnel diffraction is mathematically complex, it is simplified into a linear convolution filter. Experiments on images are compared with the Laplacian of Gaussian, Sobel and Canny edge detection algorithms. The experimental results indicate that the new detector's result is comparable to Canny detector and agree more with human's recognition. And it also can get an even better edge map on some regions which contain abundant local details or some tiny changes.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Novel low power supply DC-coupled 1.25 Gb/s laser diode driver

引用

Guti Dianzixue Yanjiu Yu Jinzhan/Research and Progress of Solid State Electronics 2006年第4期26卷 498-503页

作者： Fu, Shengmeng Chen, Zhaoyang Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory for Image Information Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

Since the DC-coupled interface between the driver and the laser diode makes it impossible for the conventional drivers to work with low power supply, an output stage has been proposed. A novel APC can suppress the output average optical power and extinction ratio within ±0.3 dBm and ±0.4 dB(-40°C to 100°C), respectively. The initialization time is not more than 0.6 μs because the fast binary search algorithm is incorporated into the APC. The burst-on delay and burst-off delay are less than 5 ns and meet the requirement of PON system. The chip is fabricated in TSMC 0.8 μm BiCMOS process and occupies an area of 1.56 mm × 1.67 mm with a power consumption of 105 mW.

关键词： Diodes

来源：评论

学校读者我要写书评

暂无评论

Understanding the Dynamical Characteristics of Neural Networks by Universal Fuzzy Logical Framework

Understanding the Dynamical Characteristics of Neural Networ...

引用

2005 International Conference on Neural Networks and Brain(ICNN&B’05)

作者： Hong Hu Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science

ISBN: (纸本)0780394224

The analytical study of a large scale nonlinear neural network is an uneasy *** try to analyze the function of neural systems by probing into the fuzzy logical framework of the neural ceUs'dynamical *** papers investigate the relation between fuzzy logic and neural *** most investigations focus on finding new function of neural system by combining fuzzy logical and neural system. In this paper,a novel approach is used to understand the nonlinear dynamic characteristics of neural system by analyzing the fuzzy logic framework of neural *** is the only way to understand the behavior of a large scale nonlinear neural *** abstracting the fuzzy logical framework of a neural cell,our analysis enables the delicate design of network *** an example,a difficulty task to build a recurrent network model of primary visual cortex by common dynamical analysis can be easily completed by this kind approach.

关键词： Understanding the Dynamical Characteristics of Neural Networks by Universal Fuzzy Logical Framework Fuzzy

来源：评论

学校读者我要写书评

暂无评论

Formal analysis of concept-interconnection

引用

Journal of Computational information Systems 2005年第4期1卷 863-869页

作者： Lei, Yuxia Sui, Yuefei Cao, Baoxiang Wang, Yan Yu, Jiguo College of Computer Science and Technology Qufu Normal University Rizhao 276826 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China

As a suitable tool for analyzing concept interconnection formally, the theory of Formal Concept Analysis (FCA) is applied. FCA deals with formal mathematical tools and techniques to develop and analyze relationship between concepts and to develop concept structures, and concepts are important building blocks in the concept-interconnection. This paper mainly discusses how FCA can be used to support concept-interconnection analysis from an application point of view. In order to introduce our idea, two kinds of concept-interconnection and interconnection measure in detail are discussed. One is based on Concept-Backbone and the other is based on the attributes. It is seen that FCA can support the building of concept-interconnection as a learning technique, but the established concept-interconnection also can be analyzed by using techniques of FCA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：